feat: add Tessl Skill Review workflow + optimize 5 skills#2
feat: add Tessl Skill Review workflow + optimize 5 skills#2rohan-tessl wants to merge 1 commit intomohitmishra786:mainfrom
Conversation
|
@rohan-tessl is attempting to deploy a commit to the immadmohitgmailcom's projects Team on Vercel. A member of the Team first needs to authorize it. |
📝 WalkthroughWalkthroughA GitHub Actions workflow is introduced to automate skill quality reviews on pull requests. Five skill documentation files are updated with Changes
Poem
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.github/workflows/skill-review.yml:
- Around line 18-19: The workflow is using mutable refs for actions; locate the
two steps that reference "uses: actions/checkout@v4" and "uses:
tesslio/skill-review@main" and replace their tags with immutable commit SHAs
(e.g., actions/checkout@<commit-sha> and tesslio/skill-review@<commit-sha>) by
looking up the appropriate commit SHA for each repository and substituting the
tag with that SHA to pin the workflow to exact commits.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 6870ccf2-7436-44e5-a01a-b8beb91907a9
📒 Files selected for processing (6)
.github/workflows/skill-review.ymlskills/build-systems/ninja/SKILL.mdskills/compilers/cpp-modules/SKILL.mdskills/debuggers/lldb/SKILL.mdskills/rust/cargo-workflows/SKILL.mdskills/rust/rust-no-std/SKILL.md
📜 Review details
🧰 Additional context used
🪛 LanguageTool
skills/rust/rust-no-std/SKILL.md
[style] ~29-~29: Using many exclamation marks might seem excessive (in this case: 4 exclamation marks for a text that’s 2715 characters long)
Context: ...st my no_std crate on my laptop?" → use #![cfg_attr(not(test), no_std)] to allow ...
(EN_EXCESSIVE_EXCLAMATION)
🔇 Additional comments (8)
skills/build-systems/ninja/SKILL.md (1)
4-13: Looks good — frontmatter routing metadata is clear and aligned with intent.
user-invocableplus focused trigger phrases should improve skill activation coverage without altering behavior.skills/compilers/cpp-modules/SKILL.md (1)
4-13: Good metadata update for discoverability.The new triggers map well to common C++20 modules questions and match the skill’s scope.
skills/debuggers/lldb/SKILL.md (1)
4-13: Nice addition — intent routing is broad but still precise.This should help activate the LLDB skill for migration, IDE, and Apple-platform debugging queries.
skills/rust/cargo-workflows/SKILL.md (1)
4-13: Solid frontmatter enhancement.The added trigger phrases are well-targeted for workspace/features/CI dependency-management use cases.
skills/rust/rust-no-std/SKILL.md (3)
3-13: Great scope clarification in frontmatter.The description and trigger set are specific and should improve correct skill invocation.
21-24: Nice content restructure.Replacing the trigger-style section with explicit “When to Use” guidance improves usability for agents.
25-29: Examples are strong and actionable.These user-intent examples make the no_std boundary and host-testing strategy immediately clear.
.github/workflows/skill-review.yml (1)
5-16: Trigger and permission scope looks good.
pull_request+ path filtering and least-privilege permissions (contents: read,pull-requests: write) are well scoped.
| - uses: actions/checkout@v4 | ||
| - uses: tesslio/skill-review@main |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
fd -p '.github/workflows' -e yml -e yaml | while read -r wf; do
echo "== $wf =="
rg -n 'uses:\s*[^[:space:]]+@[^[:space:]]+' "$wf" || true
done
echo
echo "Potentially non-pinned refs (not 40-hex SHA):"
fd -p '.github/workflows' -e yml -e yaml | while read -r wf; do
rg -nP 'uses:\s*[^@\s]+@(?!(?:[a-f0-9]{40})\b)[^\s]+' "$wf" || true
doneRepository: mohitmishra786/low-level-dev-skills
Length of output: 125
🏁 Script executed:
cat .github/workflows/skill-review.yml 2>/dev/null || echo "File not found"Repository: mohitmishra786/low-level-dev-skills
Length of output: 604
Pin GitHub Actions to immutable commit SHAs.
actions/checkout@v4 and tesslio/skill-review@main use mutable refs that can silently change at runtime. Pinning to commit SHAs hardens the workflow supply-chain integrity.
Suggested fix
- - uses: actions/checkout@v4
- - uses: tesslio/skill-review@main
+ - uses: actions/checkout@3a9c3f61038b120269fcea9c18dd1d7fc67f48b1
+ - uses: tesslio/skill-review@<commit-sha>🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.github/workflows/skill-review.yml around lines 18 - 19, The workflow is
using mutable refs for actions; locate the two steps that reference "uses:
actions/checkout@v4" and "uses: tesslio/skill-review@main" and replace their
tags with immutable commit SHAs (e.g., actions/checkout@<commit-sha> and
tesslio/skill-review@<commit-sha>) by looking up the appropriate commit SHA for
each repository and substituting the tag with that SHA to pin the workflow to
exact commits.
1 participant
Hey @mohitmishra786 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:Skill Score Improvements
What Changed
user-invocable: trueandtriggerslist to 4 skills missing frontmatter fieldsGitHub Action Added
.github/workflows/skill-review.yml— runs on every PR that touches aSKILL.mdfile and posts a score comment. No secrets required.Benefits of
tesslio/skill-reviewfail-threshold: 70to block low-quality skill mergesWant Automatic Skill Optimization Too?
tesslio/skill-review-and-optimizeChecking this box means we'll raise a second PR that adds the optimization action, which automatically rewrites low-scoring SKILL.md files on every push and opens a PR with the improvements.
Raised by Tessl · Skill Review docs
Summary by CodeRabbit
Chores
Documentation
Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute.
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me — @rohan-tessl — if you hit any snags.
Thanks in advance 🙏